qwen3:0.6b
OLLAMA GGUFqwen3 · 751.63M · Q4_K_M
Mar 2, 2026 · Apple M4
rnj-1:8b
OLLAMA GGUFgemma3 · 8.3B · Q4_K_M
Aug 24, 2026 · Apple M1 Pro
Global Score
61 vs 80
Hardware Fit
100 vs 93
Quality Score
44 vs 74
Hardware
qwen3:0.6b rnj-1:8b
MachineMacBook AirMacBook Pro
CPUApple M4Apple M1 Pro
Cores1010
RAM32 GB16 GB
GPUApple M4Apple M1 Pro
OSmacOS 26.3macOS 26.6.2
Archarm64arm64
Power Modebalancedbalanced
Performance
qwen3:0.6b rnj-1:8b
Tokens/sec144.322.3
First chunkN/A404 ms
TTFT81 ms404 ms
Load time0.9 s3.7 s
Memory usage4.1 GB8.3 GB
Memory %13%52%
HW Fit Score Breakdown
qwen3:0.6b
Speed
40/50
TTFT
30/20
Memory
30/30
rnj-1:8b
Speed
49/50
TTFT
20/20
Memory
24/30
Quality
qwen3:0.6b
Reasoning
6/20
Coding
4/20
Instruction
10/20
Structured
13/15
Math
6/15
Multilingual
5/10
Reasoning: Weak Coding: Poor Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Weak
rnj-1:8b
Reasoning
12/20
Coding
19/20
Instruction
15/20
Structured
5/15
Math
14/15
Multilingual
9/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Weak Math: Strong Multilingual: Strong
Run yours and compare
$
npm install -g metrillm@latest$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest